Skip to main content
Internet Archive's 25th Anniversary Logo

View Post [edit]

Poster: shrI_anirvAN_rachanAvali Date: Aug 26, 2021 9:50am
Forum: texts Subject: Will updating the language metadata initiate OCR

I recently came to know that archive supports OCR for devanagari script (I'm specifically interested in sanskrit and hindi languages) and bengali script via tesseract. I also noticed that my uploads (from two years ago) haven't yet been OCRed, with the message "language currently not OCRable" in the ocr metadata field.

My question is will simply updating the language metadata again add my files to the OCR queue? Or is there something else I can do to have archive OCR the files I've already uploaded?

Thanks.

Reply [edit]

Poster: Jeff Kaplan Date: Aug 27, 2021 7:57am
Forum: texts Subject: Re: Will updating the language metadata initiate OCR

i re-ran them and they now should have better ocr files.

Reply [edit]

Poster: shrI_anirvAN_rachanAvali Date: Aug 28, 2021 10:07am
Forum: texts Subject: Re: Will updating the language metadata initiate OCR

Thank you Jeff, I appreciate it very much!